|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base-960h |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: 960h |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# 960h |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5325 |
|
- Wer: 24.4442 |
|
- Cer: 12.0113 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0001 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2000 |
|
- training_steps: 2700 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:| |
|
| 1.0759 | 1.75 | 500 | 0.7781 | 32.9761 | 16.6493 | |
|
| 0.8049 | 3.51 | 1000 | 0.6552 | 29.8584 | 14.9333 | |
|
| 0.7047 | 5.26 | 1500 | 0.6050 | 27.5232 | 13.6151 | |
|
| 0.6339 | 7.02 | 2000 | 0.5865 | 26.3889 | 13.1279 | |
|
| 0.5331 | 8.77 | 2500 | 0.5325 | 24.4442 | 12.0113 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 1.12.1+cu116 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
